We were using v_readlane_b32 with the lane set to zero, but this won't
work if thread 0 is not active.
Differential Revision: http://reviews.llvm.org/D19745
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@268295
91177308-0d34-0410-b5e6-
96231b3b80d8
.addImm(i * 4) // offset
.addMemOperand(MMO);
BuildMI(*MBB, MI, DL,
- TII->getMCOpcodeFromPseudo(AMDGPU::V_READLANE_B32), SubReg)
+ TII->get(AMDGPU::V_READFIRSTLANE_B32), SubReg)
.addReg(TmpReg, RegState::Kill)
- .addImm(0)
.addReg(MI->getOperand(0).getReg(), RegState::ImplicitDefine);
}
}
; Make sure we are handling hazards correctly.
; CHECK: buffer_load_dword [[VHI:v[0-9]+]], off, s[{{[0-9]+:[0-9]+}}], s{{[0-9]+}} offset:12
; CHECK-NEXT: s_waitcnt vmcnt(0)
-; CHECK-NEXT: v_readlane_b32 s[[HI:[0-9]+]], [[VHI]]
+; CHECK-NEXT: v_readfirstlane_b32 s[[HI:[0-9]+]], [[VHI]]
; CHECK-NEXT: s_nop 4
; CHECK-NEXT: buffer_store_dword v0, off, s[0:[[HI]]{{\]}}, 0
; CHECK: s_endpgm